Skills lllllllama rigorpilot-skills RigorPilot

explore-run

Use it when:: You've authorized quick experiments on a research baseline: small-subset checks, short training probes, batch sweeps, idle-GPU searches or transfer-learning trials.
It does:: Plans candidate runs from the variants, subset sizes and step counts you set, ranks them by cost, chance of success and expected gain, and trims them to budget.
You get:: An explore_outputs/ folder ranking the runs, with what changed and where a comparison isn't fair.
Hands off:: The actual runs to minimal-run-and-audit or run-train.
Unlike run-train:: Its results are labeled candidate evidence, never trusted or state-of-the-art results.

Skill 11 of 11 in the RigorPilot bundle, after explore-code.

Only works inside its bundle: Its report script loads a shared writer that ships inside ai-research-reproduction, the repo's main skill, and stops with an error without it. Install RigorPilot instead.

TL;DR

The run step of RigorPilot's exploration lane, which tries new ideas on top of a reproduced baseline, kept apart from the reproduction itself. It works only when you explicitly ask for exploration. You describe the grid of variants to try, the subset sizes and short-run step counts, and optionally how to weigh cost, chance of success and expected gain; the default weights stay conservative. A bundled planner scores the candidates and cuts them to your limits on variants and short runs. Small, short checks come before heavier ones, and once runs have executed, ranking switches from these estimates to measured results, ordered by the metric you named. Experiment state stays separate from the trusted baseline, results are summarized for you to review, and nothing moves into the trusted lane automatically. It doesn't rewrite training logic.

Summarizes the skill at fb3ccdf.

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill explore-run

skills.sh page Source on GitHub All skills from lllllllama/rigorpilot-skills

Total Downloads: 352,178 on skills.sh, Nov 9, 2026
Repo stars: 486 lllllllama/rigorpilot-skills
First seen: Apr 1, 2026 on skills.sh

Weekly Downloads

7.3K

+48307% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	15
Sep 28	23
Oct 5	23
Oct 12	3,486
Oct 19	10,899
Oct 26	11,027
Nov 2	8,739
Nov 9	7,261

Category	category:science Research reproduction, financial data, charts and diagrams.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	ml-research
Stack	stack:python

SKILL.md

From lllllllama/rigorpilot-skills at fb3ccdf. Checked daily, last changed Nov 6, 2026.

Frontmatter

name: explore-run
description: Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline execution, conservative training verification, default routing, verified SOTA claims, or implicit experimentation.

explore-run

Use this as the Rigor Improve / Rigor Explore run leaf skill. The installed slug remains explore-run for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide candidate run planning while preserving model judgment about the active repo.

When to apply

When the researcher explicitly authorizes exploratory runs.
When the task is a small-subset validation, short-cycle training probe, batch sweep, idle-GPU search, or quick transfer-learning trial.
When the output should rank candidate runs rather than certify trusted success.

When not to apply

When the user wants trusted training execution or conservative verification.
When there is no explicit exploratory authorization.
When the task is repository setup, intake, or debugging.

Clear boundaries

This skill owns exploratory execution planning and summary only.
Use ai-research-explore instead when the task spans both current_research coordination and exploratory code changes.
It may hand off actual command execution to minimal-run-and-audit or run-train.
It should keep experiment state isolated from the trusted baseline.
It should prefer small-subset and short-cycle checks before heavier exploratory runs.
It should label run results as bounded evidence and explain when a comparison is not directly fair.

Ranking Semantics

Pre-execution candidate selection uses three factors: cost, success_rate, and expected_gain.
Default weights should stay conservative unless the researcher explicitly provides selection_weights.
Budget pruning still applies after scoring through max_variants and max_short_cycle_runs.
If runs are executed later, downstream ranking should switch to real execution evidence, not stay purely heuristic.

Variant Spec Hints

Use variant_axes to define the candidate dimension grid.
Use subset_sizes and short_run_steps to express exploratory run scale.
Use selection_weights to rebalance cost, success_rate, and expected_gain.
Use primary_metric and metric_goal so downstream ranking can order executed candidates consistently.

Output expectations

explore_outputs/CHANGESET.md
explore_outputs/SCIENTIFIC_CHANGELOG.md
explore_outputs/COMPARABILITY_REPORT.md
explore_outputs/TOP_RUNS.md
explore_outputs/status.json

Notes

Use references/execution-policy.md, ../ai-research-reproduction/references/explore-variant-spec.md, ../ai-research-reproduction/references/deep-learning-experiment-principles.md, scripts/plan_variants.py, and scripts/write_outputs.py.